Deep Learning Methods on High- Resolution Image and Video – A Profound Assessment

The clinical utility of regional strain measurements in echocardiography is challenged by suboptimal reproducibility. In this study, we aimed to evaluate the test-retest reproducibility of regional longitudinal strain (RLS) per coronary artery perfusion territory (RLSTerritory) and basal-to-apical level of the left ventricle (RLSLevel), measured by a novel fully automated deep learning (DL) method based on point tracking. We measured strain in a dual-centre test-retest data set that included 40 controls and 40 patients with suspected non-ST elevation acute coronary syndrome. Two consecutive echocardiograms per subject were recorded by different operators. The reproducibility of RLSTerritory and RLSLevel measured by the DL method and by three experienced observers using semi-automatic software (2D Strain, EchoPAC, GE HealthCare) was evaluated as minimal detectable change (MDC). The DL method had MDC for RLSTerritory and RLSLevel ranging from 3.6 to 4.3%, corresponding to a 33-35% improved reproducibility compared with the inter- and intraobserver scenarios (MDC 5.5-6.4% and 4.9-5.4%). Furthermore, the DL method had a lower variance of test-retest differences for both RLSTerritory and RLSLevel compared with inter- and intraobserver scenarios (all P < 0.001). Bland-Altman analyses demonstrated superior reproducibility by the DL method for the whole range of strain values compared with the best observer scenarios. The feasibility of the DL method was 93% and measurement time was only 1 s per echocardiogram. The novel DL method provided fully automated measurements of RLS, with improved test-retest reproducibility compared with semi-automatic measurements by experienced observers. RLS measured by the DL method has the potential to advance patient care through a more detailed, more efficient, and less user-dependent clinical assessment of myocardial function.

Less than 10% of patients with cancer have detectable pathogenic germline alterations, which may be partially due to incomplete pathogenic variant detection. To evaluate if deep learning approaches identify more germline pathogenic variants in patients with cancer. A cross-sectional study of a standard germline detection method and a deep learning method in 2 convenience cohorts with prostate cancer and melanoma enrolled in the US and Europe between 2010 and 2017. The final date of clinical data collection was December 2017. Germline variant detection using standard or deep learning methods. The primary outcomes included pathogenic variant detection performance in 118 cancer-predisposition genes estimated as sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The secondary outcomes were pathogenic variant detection performance in 59 genes deemed actionable by the American College of Medical Genetics and Genomics (ACMG) and 5197 clinically relevant mendelian genes. True sensitivity and true specificity could not be calculated due to lack of a criterion reference standard, but were estimated as the proportion of true-positive variants and true-negative variants, respectively, identified by each method in a reference variant set that consisted of all variants judged to be valid from either approach. The prostate cancer cohort included 1072 men (mean [SD] age at diagnosis, 63.7 [7.9] years; 857 [79.9%] with European ancestry) and the melanoma cohort included 1295 patients (mean [SD] age at diagnosis, 59.8 [15.6] years; 488 [37.7%] women; 1060 [81.9%] with European ancestry). The deep learning method identified more patients with pathogenic variants in cancer-predisposition genes than the standard method (prostate cancer: 198 vs 182; melanoma: 93 vs 74); sensitivity (prostate cancer: 94.7% vs 87.1% [difference, 7.6%; 95% CI, 2.2% to 13.1%]; melanoma: 74.4% vs 59.2% [difference, 15.2%; 95% CI, 3.7% to 26.7%]), specificity (prostate cancer: 64.0% vs 36.0% [difference, 28.0%; 95% CI, 1.4% to 54.6%]; melanoma: 63.4% vs 36.6% [difference, 26.8%; 95% CI, 17.6% to 35.9%]), PPV (prostate cancer: 95.7% vs 91.9% [difference, 3.8%; 95% CI, -1.0% to 8.4%]; melanoma: 54.4% vs 35.4% [difference, 19.0%; 95% CI, 9.1% to 28.9%]), and NPV (prostate cancer: 59.3% vs 25.0% [difference, 34.3%; 95% CI, 10.9% to 57.6%]; melanoma: 80.8% vs 60.5% [difference, 20.3%; 95% CI, 10.0% to 30.7%]). For the ACMG genes, the sensitivity of the 2 methods was not significantly different in the prostate cancer cohort (94.9% vs 90.6% [difference, 4.3%; 95% CI, -2.3% to 10.9%]), but the deep learning method had a higher sensitivity in the melanoma cohort (71.6% vs 53.7% [difference, 17.9%; 95% CI, 1.82% to 34.0%]). The deep learning method had higher sensitivity in the mendelian genes (prostate cancer: 99.7% vs 95.1% [difference, 4.6%; 95% CI, 3.0% to 6.3%]; melanoma: 91.7% vs 86.2% [difference, 5.5%; 95% CI, 2.2% to 8.8%]). Among a convenience sample of 2 independent cohorts of patients with prostate cancer and melanoma, germline genetic testing using deep learning, compared with the current standard genetic testing method, was associated with higher sensitivity and specificity for detection of pathogenic variants. Further research is needed to understand the relevance of these findings with regard to clinical outcomes.

Deep learning methods have become popular among researchers in the field of fault detection. However, their performance depends on the availability of big datasets. To overcome this problem researchers started applying transfer learning to achieve good performance from small available datasets, by leveraging multiple prediction models over similar machines and working conditions. However, the influence of negative transfer limits their application. Negative transfer among prediction models increases when the environment and working conditions are changing continuously. To overcome the effect of negative transfer, we propose a novel deep transfer learning method, coined deep boosted transfer learning, for wind turbine gearbox fault detection that prevents negative transfer and only focuses on relevant information from the source machine. The proposed method is an instance-based deep transfer learning method that updates the weights of the source and the target machine training samples separately. The weights of different source training samples are gradually decreased to reduce the impact on the final model. The proposed method is verified by the Case Western Reserve University bearing and real field wind farm datasets. The results show that the proposed method ignores negative transfer and achieves higher accuracy compared to standard deep learning and deep transfer learning methods.

This review paper examines the current state of lung disease diagnosis based on deep learning (DL) methods. Lung diseases, such as Pneumonia, TB, Covid-19, and lung cancer, are significant causes of morbidity and mortality worldwide. Accurate and timely diagnosis of these diseases is essential for effective treatment and improved patient outcomes. DL methods, which utilize artificial neural networks to extract features from medical images automatically, have shown great promise in improving the accuracy and efficiency of lung disease diagnosis. This review discusses the various DL methods that have been developed for lung disease diagnosis, including convolutional neural networks (CNNs), deep neural networks (DNNs), and generative adversarial networks (GANs). The advantages and limitations of each method are discussed, along with the types of medical imaging techniques used, such as X-ray and computed tomography (CT). In addition, the review discusses the most commonly used performance metrics for evaluating the performance of DL for lung disease diagnosis: the area under the curve (AUC), sensitivity, specificity, F1-score, accuracy, precision, and the receiver operator characteristic curve (ROC). Moreover, the challenges and limitations of using DL for lung disease diagnosis, including the limited availability of annotated data, the variability in imaging techniques and disease presentation, and the interpretability and generalizability of DL models, are highlighted in this paper. Furthermore, strategies to overcome these challenges, such as transfer learning, data augmentation, and explainable AI, are also discussed. The review concludes with a call for further research to address the remaining challenges and realize DL's full potential for improving lung disease diagnosis and treatment.

ObjectivePituitary adenomas are the most common type of pituitary disorders, which usually occur in young adults and often affect the patient’s physical development, labor capacity and fertility. Clinical free texts noted in electronic medical records (EMRs) of pituitary adenomas patients contain abundant diagnosis and treatment information. However, this information has not been well utilized because of the challenge to extract information from unstructured clinical texts. This study aims to enable machines to intelligently process clinical information, and automatically extract clinical named entity for pituitary adenomas from Chinese EMRs.MethodsThe clinical corpus used in this study was from one pituitary adenomas neurosurgery treatment center of a 3A hospital in China. Four types of fine-grained texts of clinical records were selected, which included notes from present illness, past medical history, case characteristics and family history of 500 pituitary adenoma inpatients. The dictionary-based matching, conditional random fields (CRF), bidirectional long short-term memory with CRF (BiLSTM-CRF), and bidirectional encoder representations from transformers with BiLSTM-CRF (BERT-BiLSTM-CRF) were used to extract clinical entities from a Chinese EMRs corpus. A comprehensive dictionary was constructed based on open source vocabularies and a domain dictionary for pituitary adenomas to conduct the dictionary-based matching method. We selected features such as part of speech, radical, document type, and the position of characters to train the CRF-based model. Random character embeddings and the character embeddings pretrained by BERT were used respectively as the input features for the BiLSTM-CRF model and the BERT-BiLSTM-CRF model. Both strict metric and relaxed metric were used to evaluate the performance of these methods.ResultsExperimental results demonstrated that the deep learning and other machine learning methods were able to automatically extract clinical named entities, including symptoms, body regions, diseases, family histories, surgeries, medications, and disease courses of pituitary adenomas from Chinese EMRs. With regard to overall performance, BERT-BiLSTM-CRF has the highest strict F1 value of 91.27% and the highest relaxed F1 value of 95.57% respectively. Additional evaluations showed that BERT-BiLSTM-CRF performed best in almost all entity recognition except surgery and disease course. BiLSTM-CRF performed best in disease course entity recognition, and performed as well as the CRF model for part of speech, radical and document type features, with both strict and relaxed F1 value reaching 96.48%. The CRF model with part of speech, radical and document type features performed best in surgery entity recognition with relaxed F1 value of 95.29%.ConclusionsIn this study, we conducted four entity recognition methods for pituitary adenomas based on Chinese EMRs. It demonstrates that the deep learning methods can effectively extract various types of clinical entities with satisfying performance. This study contributed to the clinical named entity extraction from Chinese neurosurgical EMRs. The findings could also assist in information extraction in other Chinese medical texts.

According to a recently conducted survey on surgical complication mortality rate, 47% of such cases are due to anesthetics overdose. This indicates that there is an urgent need to moderate the level of anesthesia. Recently deep learning (DL) methods have played a major role in estimating the depth of Anesthesia (DOA) of patients and has played an essential role in control anesthesia overdose. In this paper, Electroencephalography (EEG) signals have been used for the prediction of DOA. EEG signals are very complex signals which may require months of training and advanced signal processing techniques. It is a point of debate whether DL methods are an improvement over the already existing traditional EEG signal processing approaches. One of the DL algorithms is Convolutional neural network (CNN) which is very popular algorithm for object recognition and is widely growing its applications in processing hierarchy in the human visual system. In this paper, various decomposition methods have been used for extracting the features EEG signal. After acquiring the necessary signals values in image format, several CNN models have been deployed for classification of DOA depending upon their Bispectral Index (BIS) and the signal quality index (SQI). The EEG signals were converted into the frequency domain using and Empirical Mode Decomposition (EMD), and Ensemble Empirical Mode Decomposition (EEMD). However, because of the inter mode mixing observed in EMD method; EEMD have been utilized for this study. The developed CNN models were used to predict the DOA based on the EEG spectrum images without the use of handcrafted features which provides intuitive mapping with high efficiency and reliability. The best trained model gives an accuracy of 83.2%. Hence, this provides further scope and research which can be carried out in the domain of visual mapping of DOA using EEG signals and DL methods.

Steady State Motion Visual Evoked Potential (SSMVEP)-based Brain Computer Interface (BCI) is widely studied and has been used to varies of occasions on account of its good performance, mild stimulation, and free of additional training. We design a trolley control system based on SSMVEP signals and observe a phenomenon named “BCI Illiterate,” in which case some subjects present unsatisfactory performance with low classification accuracies. In order to cope with this challenging problem in real-world contexts, we introduce a deep learning (DL) method. The method allows improving the accuracies for both EEG literate and EEG illiterate. In particular, we firstly conduct SSMVEP experiments to obtain EEG signals from 10 subjects, including 5 EEG literates and 5 EEG illiterates. Then we construct a convolutional neural network with long short-term memory (CNN-LSTM) framework, which allows extracting the spectral, spatial, and temporal features of EEG signals, to realize the high classification accuracies of SSMVEP signals. The results show that DL method can reach 96.83% and 91.86% for EEG literate and EEG illiterate respectively, which are 12.68% and 31.08% higher than the results of traditional methods. These results indicate that DL method is not only suitable for EEG literate, but more importantly, can greatly improve the performance for EEG illiterate, which finally can enhance the robustness and universality of the SSMVEP-based BCI.

The comprehensive use of high-resolution remote sensing (HRS) images and deep learning (DL) methods can be used to further accurate urban green space (UGS) mapping. However, in the process of UGS segmentation, most of the current DL methods focus on the improvement of the model structure and ignore the spectral information of HRS images. In this paper, a multiscale attention feature aggregation network (MAFANet) incorporating feature engineering was proposed to achieve segmentation of UGS from HRS images (GaoFen-2, GF-2). By constructing a new decoder block, a bilateral feature extraction module, and a multiscale pooling attention module, MAFANet enhanced the edge feature extraction of UGS and improved segmentation accuracy. By incorporating feature engineering, including false color image and the Normalized Difference Vegetation Index (NDVI), MAFANet further distinguished UGS boundaries. The UGS labeled datasets, i.e., UGS-1 and UGS-2, were built using GF-2. Meanwhile, comparison experiments with other DL methods are conducted on UGS-1 and UGS-2 to test the robustness of the MAFANet network. We found the mean Intersection over Union (MIOU) of the MAFANet network on the UGS-1 and UGS-2 datasets was 72.15% and 74.64%, respectively; outperforming other existing DL methods. In addition, by incorporating false color image in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.64%; by incorporating vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.09%; and by incorporating false color image and the vegetation index (NDVI) in UGS-1, the MIOU of MAFANet was improved from 72.15% to 74.73%. Our experimental results demonstrated that the proposed MAFANet incorporating feature engineering (false color image and NDVI) outperforms the state-of-the-art (SOTA) methods in UGS segmentation, and the false color image feature is better than the vegetation index (NDVI) for enhancing green space information representation. This study provided a practical solution for UGS segmentation and promoted UGS mapping.

Automatic assessment of pain based on deep learning methods: A systematic review

The sixth generation (6G) of wireless communication networks should deliver higher data rates and spectral efficiency for novel demands and utilizations. Cell free massive MIMO is one promising technique to achieve these goals. Distribution of base stations (BSs) in this system creates more efficiency and better coverage of users than the conventional cellular system. On the other hand, deep learning methods have been proven to be competitive frameworks in comparison of traditional optimization approaches in wireless communication applications. In this paper, power allocation in cell free massive MIMO system in uplink transmission is investigated. Firstly, we achieve lower bound of spectral efficiency, which is valid for all decoders. Besides, we evaluate MAX- MIN power allocation problem from the perspective of deep learning and common optimization methods. The simulation results confirm the superior performance of the deep learning compared to traditional optimization methods. Furthermore, computations complexity of power allocation in the deep learning case are extremely low.

This paper compares the ability of deep learning and entropic learning methods to predict the probability of the Niño-3.4 index being above 0.4° (El Niño), below −0.4° (La Niña), or within both of these thresholds (neutral) at lead times of 3 up to 24 months. In particular, the performance, interpretability, and training cost of entropic learning methods, represented by the entropy-optimal scalable probabilistic approximation (eSPA) algorithm, are compared with deep learning methods, represented by a long short-term memory (LSTM) classifier, trained on the same dataset. Using only monthly data derived from a surface-forced ocean model over the period 1958–2018, the problem manifests as a canonical small-data challenge. Relative to the LSTM model, eSPA exhibits equivalent or better performance in terms of area under the receiver operating characteristic curve (AUC) for all lead times with a smaller computational cost by two and three orders of magnitude. Comparisons of AUC with other state-of-the-art deep learning models in the literature show that eSPA appears to also be more accurate than these models across all three classes. Composite images are generated for each of the cluster centroids from each trained eSPA model at each lead time. At shorter lead times, the composite images for the most significant clusters correspond to patterns representing mature or emerging/declining El Niño or La Niña states, while at longer lead times, they correspond to precursor states consisting of extratropical anomalies. Finally, modifications to the baseline dataset are explored, showing that improvements can be made in the parsimony of the trained eSPA model without sacrificing predictive power.

Thermal load forecasting in district heating networks using deep learning and advanced feature selection methods

Excessive withdrawal of groundwater for agricultural irrigation can cause seawater intrusion into coastal aquifers. Such a case will in turn results in deterioration of irrigation water quality. Determination of irrigation water quality with traditional methods is a time-consuming and costly process. However, machine learning algorithms can be useful tools for modeling and estimating groundwater quality used for irrigation water purposes. In this study, TDS, PS, SAR, and Cl parameters of groundwater were estimated with models based on EC and pH variables. For this purpose, prediction performances of two different deep learning methods (convolutional neural network (CNN) and deep neural network (DNN)) and two different classical machine learning (Random Forest (RF) and extreme gradient boosting (XGBoost)) methods were compared. In addition, predictive uncertainty of the models was determined by quantile regression (QR) analysis. Performance criteria and results of uncertainty analysis revealed that CNN (in testing phase, NSE = 0.95 for TDS, NSE = 0.96 for PS, NSE = 0.67 for SAR and NSE = 0.93 for CI) and DNN (in testing phase, NSE = 0.91 for TDS, NSE = 0.91 for PS, NSE = 0.57 for SAR and NSE = 0.94 for Cl) models had quite a close performance in estimation of TDS, PS, SAR, and Cl parameters and higher than the other two classical machine learning methods. As a result, the CNN model can be considered the best performing model in estimating all quality parameters due to the highest NSE and lowest RMSE values. In addition, the Taylor diagram showed that the values estimated using the CNN model had the highest correlation with the measured data. It was determined that the model with the lowest uncertainty based on the PICP statistics was DNN, followed by the CNN model. However, the CNN model has predicted outliers more accurately. Present findings proved that deep learning models could offer efficient tools for predicting irrigation water quality parameters.

Software vulnerabilities (SV) cause disastrous impact on information security in recent years. Higher cost and time consumption on manual detection methods lead to enormous number of increase in automatic SV detection techniques. Machine learning, deep learning (DL) and data mining methods are the most popular and efficient ones which also have advantage on analyzing performance results with use of available open-source softwares. This survey mainly focuses on the recent SV detection systems that use deep learning techniques. In this context, papers with significant impact on the literature are investigated, and deep learning methods, data sets and performance results are analyzed. Moreover, open problems and solution proposals are discussed.

Cardiovascular diseases (CVDs) remain a leading cause of global mortality, underscoring the urgent need for early and accurate diagnosis. Electrocardiograms (ECGs) are a widely used, noninvasive tool for detecting cardiac abnormalities, but manual interpretation can be time- consuming and prone to error. This study explores advanced machine learning (ML) and deep learning (DL) methods to improve the detection of CVDs from ECG images, leveraging their ability to analyze complex patterns with high precision. Models such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and ensemble frameworks are utilized, alongside traditional ML models like XGBoost, CatBoost, and LightGBM. The performance of these models is evaluated based on precision, recall, F1-score, and accuracy. Results show that DL models, particularly an ensemble of CNN and ViT, achieve superior accuracy , outperforming standalone ML methods. Furthermore, an ensemble of XGBoost, CatBoost, and LightGBM achieves competitive results, while Optuna-tuned XGBoost further enhances ML performance. The findings highlight the potential of combining ML and DL techniques for robust and reliable CVD detection in ECG images. This research demonstrates the promise of AI-driven solutions in advancing medical diagnostics and supports the integration of automated systems for early detection of cardiovascular diseases.